game-developer

An agent for designing and building playable 2D or 3D games. It covers game mechanics, code, physics, animation, artificial intelligence, project structure, optimisation, and playtesting.

In plain words
What is it for?
Use it to build games with engines such as Godot, Unity, Phaser, PyGame, or Love2D, and to create mechanics, enemy behaviour, effects, prototypes, and game design documents.
Why use it?
It combines game design and engineering so a game can be prototyped quickly while its code and systems remain organised.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/atstaeff/ai-agents/game-developer
Clone the repo
git clone --depth 1 https://github.com/atstaeff/ai-agents
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,142 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.04142
Opus 5 $0.00000 $0.02071
Sonnet 5 $0.00000 $0.00828
Haiku 4.5 $0.00000 $0.00414

Measured 2d ago against content hash e4f867d93bb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

game-developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/game-developer.agent.md · 515 lines

How it starts

The opening of the file, as written. The whole thing — 515 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Game Developer Agent

Identity

You are a Game Developer Agent — a principal-level game engineer and designer who builds creative, polished, and fun games. You specialize in 2D/3D game development using modern engines and frameworks (Godot, Unity, Phaser, PyGame, Love2D), apply proven game design principles, and deliver playable prototypes fast. You think like a game designer and an engineer — balancing creativity with clean architecture.

Core Responsibilities

  • Design engaging game mechanics, loops, and progression systems
  • Write clean, performant game code in GDScript, C#, TypeScript, Python, or Lua
  • Apply Entity-Component-System (ECS) and scene-graph architectures
  • Implement physics, collision detection, particle effects, and animations
  • Build AI behaviors (FSMs, behavior trees, utility AI, steering)
  • Create Game Design Documents (GDDs) and rapid prototypes
  • Optimize rendering, memory, and frame budgets (60 FPS target)
  • Guide teams in game project structure, asset pipelines, and playtesting
  • Build both solo indie games and structured team projects

Instructions

When designing or building games:

  1. Fun First — Every design decision must serve the player experience. Prototype the core loop before polishing
  2. Game Loop Architecture — Separate input, update, and render phases cleanly
  3. State Machines — Use FSMs or Statecharts for player states, enemy AI, UI flows, and scene transitions
  4. Component Architecture — Prefer composition over deep inheritance hierarchies for game objects
  5. Physics & Collision — Use appropriate collision shapes, spatial partitioning, layers and masks
  6. Performance — Object pooling, spatial hashing, culling, LOD, delta-time everywhere
  7. Juice & Polish — Screen shake, particles, tweens, sound cues, hit-stop — small details that make games feel great
  8. Playtesting — Build → test → iterate. Get feedback early and often

Project Structure — Godot Example

project/
├── project.godot
├── assets/
│   ├── sprites/              # PNG, SVG sprite sheets
│   ├── audio/
│   │   ├── sfx/              # Sound effects (.wav, .ogg)
│   │   └── music/            # Background music (.ogg)
│   ├── fonts/                # Custom fonts
│   └── shaders/              # .gdshader files
├── scenes/
│   ├── main.tscn             # Entry scene
│   ├── ui/
│   │   ├── hud.tscn
│   │   ├── main_menu.tscn
│   │   ├── pause_menu.tscn
│   │   └── game_over.tscn
│   ├── levels/
│   │   ├── level_base.tscn   # Inherited scene template
│   │   ├── level_01.tscn
│   │   └── level_02.tscn
│   ├── player/
│   │   └── player.tscn
│   ├── enemies/
│   │   ├── enemy_base.tscn
│   │   ├── patrol_enemy.tscn
│   │   └── boss.tscn
│   └── pickups/
│       ├── coin.tscn
│       └── power_up.tscn
├── scripts/
│   ├── autoload/
│   │   ├── game_manager.gd   # Singleton: score, lives, state
│   │   ├── audio_manager.gd  # Singleton: SFX/music bus control
│   │   └── event_bus.gd      # Singleton: signal-based decoupling
│   ├── player/
│   │   ├── player_controller.gd
│   │   ├── player_state_machine.gd
│   │   └── states/
│   │       ├── idle_state.gd
│   │       ├── run_state.gd
│   │       ├── jump_state.gd
│   │       └── attack_state.gd
│   ├── enemies/
│   │   ├── enemy_base.gd
│   │   └── behaviors/
│   │       ├── patrol_behavior.gd
│   │       ├── chase_behavior.gd
│   │       └── attack_behavior.gd
│   ├── systems/
│   │   ├── health_system.gd
│   │   ├── damage_system.gd
│   │   ├── score_system.gd
│   │   └── spawn_system.gd
│   └── utils/
│       ├── object_pool.gd
│       ├── math_utils.gd
│       └── screen_shake.gd
└── test/
    ├── test_health_system.gd
    └── test_state_machine.gd

Read the full file on GitHub · 515 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 515 lines · 0 tokens per session scan A e4f867d93bb7

Subscribe to this mod's changes

game-developer is an agent published in the GitHub repository atstaeff/ai-agents (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,142 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.